Zhenzhong1
ebd2ab0222
Update tuned_single_gaudi_with_rerank.yaml
2024-11-06 16:00:41 +08:00
Zhenzhong1
2f1f80bbae
fixed the issue of cm
2024-10-29 03:03:21 -07:00
Zhenzhong1
5158b5e822
updateto vllm images
2024-10-29 02:44:27 -07:00
Zhenzhong1
1c3f55602a
added vllm
2024-10-29 02:13:06 -07:00
Zhenzhong1
bb4c1dbc44
Update configmap.yaml
2024-10-28 19:36:32 +08:00
Zhenzhong1
16018085b0
added some envs
2024-10-25 09:22:36 +03:00
Zhenzhong1
93bbd5131f
updated oob manifests
2024-10-24 05:11:23 +03:00
chensuyue
4f32f867ec
update cpu core into 80
...
Signed-off-by: chensuyue <suyue.chen@intel.com >
2024-10-23 14:49:04 +08:00
Zhenzhong1
4f183c2a0d
restore README
2024-10-23 14:33:10 +08:00
Zhenzhong1
1046aad26f
removed benchmark template
2024-10-23 09:30:03 +03:00
pre-commit-ci[bot]
2876677214
[pre-commit.ci] auto fixes from pre-commit.com hooks
...
for more information, see https://pre-commit.ci
2024-10-22 09:11:46 +00:00
Zhenzhong1
a9536321a0
added the tuned tgi params
2024-10-22 12:11:22 +03:00
Zhenzhong1
24de14e58a
fixed the audioqna benchmark path
2024-10-22 11:29:30 +03:00
pre-commit-ci[bot]
065222f29b
[pre-commit.ci] auto fixes from pre-commit.com hooks
...
for more information, see https://pre-commit.ci
2024-10-22 08:19:15 +00:00
Zhenzhong1
3f596d9747
update README
2024-10-22 11:18:49 +03:00
pre-commit-ci[bot]
9da0c09b18
[pre-commit.ci] auto fixes from pre-commit.com hooks
...
for more information, see https://pre-commit.ci
2024-10-22 08:10:20 +00:00
Zhenzhong1
b9c646a2b8
update README
2024-10-22 11:09:50 +03:00
Zhenzhong1
27e9832af4
fixed visualqna issues
2024-10-22 10:40:05 +03:00
Zhenzhong1
f3cbcadfa2
fixed visualqna image issues & tgi params issues
2024-10-22 10:26:44 +03:00
Zhenzhong1
e21ee76f24
updated tgiparams
2024-10-22 09:15:11 +03:00
pre-commit-ci[bot]
8effe7a4eb
[pre-commit.ci] auto fixes from pre-commit.com hooks
...
for more information, see https://pre-commit.ci
2024-10-22 05:38:44 +00:00
Zhenzhong1
0d3876d6fa
removed multiple yamls
2024-10-22 08:38:15 +03:00
Zhenzhong1
bb46f5b355
added visual qna & update deployment template
2024-10-22 05:45:00 +03:00
Zhenzhong1
bcaffd7db4
added more cases
2024-10-21 12:21:02 +03:00
Zhenzhong1
124143ea40
removed values.yaml
2024-10-21 12:10:59 +03:00
Zhenzhong1
6dc4bb5c79
refactoered image
2024-10-21 11:54:18 +03:00
pre-commit-ci[bot]
d290bd811f
[pre-commit.ci] auto fixes from pre-commit.com hooks
...
for more information, see https://pre-commit.ci
2024-10-21 08:14:22 +00:00
Zhenzhong Xu
d68ce801e4
refactored AudioQNA
2024-10-21 11:12:29 +03:00
Zhenzhong Xu
048b4e1df9
refactored AudioQNA
2024-10-21 11:06:37 +03:00
Zhenzhong Xu
fdb8a33a6e
refactored GaqGen
2024-10-21 10:48:16 +03:00
Zhenzhong Xu
4e1237d410
refactored GaqGen
2024-10-21 10:46:12 +03:00
Zhenzhong Xu
58ff7d9518
moved HUGGINGFACEHUB_API_TOKEN
2024-10-21 10:41:20 +03:00
Zhenzhong Xu
9ee1a7410b
rename
2024-10-21 10:31:27 +03:00
Zhenzhong Xu
24166615d7
removed spec
2024-10-21 09:01:00 +03:00
Zhenzhong Xu
a0b2263fd3
updated customize deployment template
2024-10-21 08:49:38 +03:00
Zhenzhong Xu
5c2f3f0301
move image & replicas path
2024-10-21 07:04:31 +03:00
Zhenzhong Xu
a70775d3d6
updated chatqna helmcharts image name
2024-10-21 06:54:27 +03:00
Zhenzhong Xu
3dd5475773
updated chatqna helmcharts
2024-10-21 06:40:46 +03:00
Zhenzhong1
d6b04b3405
benchmark helmcharts ( #995 )
...
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2024-10-21 11:13:24 +08:00
Dina Suehiro Jones
184e9a43b8
Update AudioQnA README to add a couple usage details ( #948 )
...
Signed-off-by: Dina Suehiro Jones <dina.s.jones@intel.com >
Co-authored-by: Sihan Chen <39623753+Spycsh@users.noreply.github.com >
2024-10-21 10:22:22 +08:00
Sihan Chen
658867fce4
Add multi-language AudioQnA on Xeon ( #982 )
...
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2024-10-21 09:58:14 +08:00
chen, suyue
620ef76d16
open manifest test in CI when dockerfile changed ( #985 )
...
Signed-off-by: chensuyue <suyue.chen@intel.com >
2024-10-20 21:58:52 +08:00
Louie Tsai
23b820e740
Update Agent README.md for workflow ( #950 )
...
Signed-off-by: Tsai, Louie <louie.tsai@intel.com >
2024-10-18 23:58:04 +08:00
lvliang-intel
3c164f3aa2
Make rerank run on gaudi for hpu docker compose ( #980 )
...
Signed-off-by: lvliang-intel <liang1.lv@intel.com >
2024-10-18 21:49:36 +08:00
CharleneHu-42
7669c42085
Update ChatQnA README to add benchmark launcher ( #958 )
...
Signed-off-by: CharleneHu-42 <yabai.hu@intel.com >
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Yi Yao <yi.a.yao@intel.com >
2024-10-18 13:33:20 +08:00
lvliang-intel
256b58c07e
Replace environment variables with service name for ChatQnA ( #977 )
...
Signed-off-by: lvliang-intel <liang1.lv@intel.com >
2024-10-18 11:31:24 +08:00
jiahuit1
3c3a5bed67
Remove deprecated images in docker_images_list.md ( #979 )
...
Signed-off-by: jiahuit1 <jia1.hui.tan@intel.com >
2024-10-18 11:21:46 +08:00
ylg
37c74b232c
Update ChatQnA yaml and set retriever's TEI_EMBEDDING_ENDPOINT ( #953 )
...
Signed-off-by: longguang.yue <bigclouds@163.com >
2024-10-17 16:58:47 +08:00
Sihan Chen
4a265abb73
Fix top_n rerank docs ( #976 )
2024-10-17 15:49:16 +08:00
Sihan Chen
b0487fe92b
fix chatqna accuracy issue with incorrect penalty ( #974 )
2024-10-17 15:48:44 +08:00